X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLeiMirror.pm;h=acf086654089f4d2cbf8f0d7c25eddd01271086b;hb=fe74ddc3f2d0590727c00ee41e80f3dfc7345387;hp=ec41bec6f16b51547a9ab56bdea4279b6635e3a9;hpb=6bb8478c8dacf83492de3afe15a615d646f0904f;p=public-inbox.git diff --git a/lib/PublicInbox/LeiMirror.pm b/lib/PublicInbox/LeiMirror.pm index ec41bec6..acf08665 100644 --- a/lib/PublicInbox/LeiMirror.pm +++ b/lib/PublicInbox/LeiMirror.pm @@ -1,17 +1,25 @@ -# Copyright (C) 2021 all contributors +# Copyright (C) all contributors # License: AGPL-3.0+ # "lei add-external --mirror" support (also "public-inbox-clone"); package PublicInbox::LeiMirror; -use strict; -use v5.10.1; +use v5.12; use parent qw(PublicInbox::IPC); -use PublicInbox::Config; use IO::Uncompress::Gunzip qw(gunzip $GunzipError); use IO::Compress::Gzip qw(gzip $GzipError); use PublicInbox::Spawn qw(popen_rd spawn run_die); +use File::Path (); use File::Temp (); +use File::Spec (); use Fcntl qw(SEEK_SET O_CREAT O_EXCL O_WRONLY); +use Carp qw(croak); +use URI; +use PublicInbox::Config; +use PublicInbox::Inbox; +use PublicInbox::LeiCurl; +use PublicInbox::OnDestroy; + +our $LIVE; # pid => callback sub _wq_done_wait { # dwaitpid callback (via wq_eof) my ($arg, $pid) = @_; @@ -19,10 +27,11 @@ sub _wq_done_wait { # dwaitpid callback (via wq_eof) my $f = "$mrr->{dst}/mirror.done"; if ($?) { $lei->child_error($?); - } elsif (!unlink($f)) { + } elsif (!$mrr->{dry_run} && !unlink($f)) { warn("unlink($f): $!\n") unless $!{ENOENT}; } else { - if ($lei->{cmd} ne 'public-inbox-clone') { + if (!$mrr->{dry_run} && $lei->{cmd} ne 'public-inbox-clone') { + # calls _finish_add_external $lei->lazy_cb('add-external', '_finish_' )->($lei, $mrr->{dst}); } @@ -33,20 +42,28 @@ sub _wq_done_wait { # dwaitpid callback (via wq_eof) # for old installations without manifest.js.gz sub try_scrape { - my ($self) = @_; + my ($self, $fallback_manifest) = @_; my $uri = URI->new($self->{src}); my $lei = $self->{lei}; my $curl = $self->{curl} //= PublicInbox::LeiCurl->new($lei) or return; - my $cmd = $curl->for_uri($lei, $uri, '--compressed'); + my $cmd = $curl->for_uri($lei, $uri, qw(-f --compressed)); my $opt = { 0 => $lei->{0}, 2 => $lei->{2} }; my $fh = popen_rd($cmd, undef, $opt); my $html = do { local $/; <$fh> } // die "read(curl $uri): $!"; close($fh) or return $lei->child_error($?, "@$cmd failed"); # we grep with URL below, we don't want Subject/From headers - # making us clone random URLs + # making us clone random URLs. This assumes remote instances + # prior to public-inbox 1.7.0 + # 5b96edcb1e0d8252 (www: move mirror instructions to /text/, 2021-08-28) my @html = split(/
/, $html); my @urls = ($html[-1] =~ m!\bgit clone --mirror ([a-z\+]+://\S+)!g); + if (!@urls && $fallback_manifest) { + warn <as_string; chop($url) eq '/' or die "BUG: $uri not canonicalized"; @@ -55,9 +72,12 @@ sub try_scrape { if (my @v2_urls = grep(m!\A\Q$url\E/[0-9]+\z!, @urls)) { my %v2_epochs = map { my ($n) = (m!/([0-9]+)\z!); - $n => URI->new($_) + $n => [ URI->new($_), '' ] } @v2_urls; # uniq - return clone_v2($self, \%v2_epochs); + clone_v2_prep($self, \%v2_epochs); + delete local $lei->{opt}->{epoch}; + clone_all($self); + return; } # filter out common URLs served by WWW (e.g /$MSGID/T/) @@ -82,47 +102,74 @@ sub clone_cmd { # e.g.: git -c http.proxy=socks5h://127.0.0.1:9050 push(@cmd, '-c', $_) for @{$lei->{opt}->{c} // []}; push @cmd, qw(clone --mirror); - push @cmd, '-q' if $lei->{opt}->{quiet}; + push @cmd, '-q' if $lei->{opt}->{quiet} || + ($lei->{opt}->{jobs} // 1) > 1; push @cmd, '-v' if $lei->{opt}->{verbose}; # XXX any other options to support? - # --reference is tricky with multiple epochs... + # --reference is tricky with multiple epochs, but handled + # automatically if using manifest.js.gz @cmd; } -sub _get_txt { # non-fatal - my ($self, $endpoint, $file) = @_; - my $uri = URI->new($self->{src}); +sub ft_rename ($$$) { + my ($ft, $dst, $open_mode) = @_; + my $fn = $ft->filename; + my @st = stat($dst); + my $mode = @st ? ($st[2] & 07777) : ($open_mode & ~umask); + chmod($mode, $ft) or croak "E: chmod $fn: $!"; + require File::Copy; + File::Copy::mv($fn, $dst) or croak "E: mv($fn => $ft): $!"; + $ft->unlink_on_destroy(0); +} + +sub _get_txt_start { # non-fatal + my ($self, $endpoint, $fini) = @_; + my $uri = URI->new($self->{cur_src} // $self->{src}); my $lei = $self->{lei}; my $path = $uri->path; chop($path) eq '/' or die "BUG: $uri not canonicalized"; $uri->path("$path/$endpoint"); - my $ft = File::Temp->new(TEMPLATE => "$file-XXXX", DIR => $self->{dst}); - my $f = $ft->filename; + my $f = (split(m!/!, $endpoint))[-1]; + my $ft = File::Temp->new(TEMPLATE => "$f-XXXX", TMPDIR => 1); my $opt = { 0 => $lei->{0}, 1 => $lei->{1}, 2 => $lei->{2} }; - my $cmd = $self->{curl}->for_uri($lei, $uri, - qw(--compressed -R -o), $f); - my $cerr = run_reap($lei, $cmd, $opt); - return "$uri missing" if ($cerr >> 8) == 22; - return "# @$cmd failed (non-fatal)" if $cerr; - my $ce = "$self->{dst}/$file"; - rename($f, $ce) or return "rename($f, $ce): $! (non-fatal)"; - $ft->unlink_on_destroy(0); + my $cmd = $self->{curl}->for_uri($lei, $uri, qw(-f --compressed -R -o), + $ft->filename); + my $jobs = $lei->{opt}->{jobs} // 1; + reap_live() while keys(%$LIVE) >= $jobs; + $lei->qerr("# @$cmd"); + return if $self->{dry_run}; + $self->{"-get_txt.$endpoint"} = [ $ft, $cmd, $uri ]; + $LIVE->{spawn($cmd, undef, $opt)} = + [ \&_get_txt_done, $self, $endpoint, $fini ]; +} + +sub _get_txt_done { # returns true on error (non-fatal), undef on success + my ($self, $endpoint) = @_; + my ($fh, $cmd, $uri) = @{delete $self->{"-get_txt.$endpoint"}}; + my $cerr = $?; + $? = 0; # don't influence normal lei exit + return warn("$uri missing\n") if ($cerr >> 8) == 22; + return warn("# @$cmd failed (non-fatal)\n") if $cerr; + seek($fh, SEEK_SET, 0) or die "seek: $!"; + $self->{"mtime.$endpoint"} = (stat($fh))[9]; + local $/; + $self->{"txt.$endpoint"} = <$fh>; undef; # success } -# tries the relatively new /$INBOX/_/text/config/raw endpoint -sub _try_config { +sub _write_inbox_config { my ($self) = @_; - my $dst = $self->{dst}; - if (!-d $dst || !mkdir($dst)) { - require File::Path; - File::Path::mkpath($dst); - -d $dst or die "mkpath($dst): $!\n"; - } - my $err = _get_txt($self, qw(_/text/config/raw inbox.config.example)); - return warn($err, "\n") if $err; - my $f = "$self->{dst}/inbox.config.example"; - chmod((stat($f))[2] & 0444, $f) or die "chmod(a-w, $f): $!"; + my $buf = delete($self->{'txt._/text/config/raw'}) // return; + my $dst = $self->{cur_dst} // $self->{dst}; + my $f = "$dst/inbox.config.example"; + open my $fh, '>', $f or die "open($f): $!"; + print $fh $buf or die "print: $!"; + chmod(0444 & ~umask, $fh) or die "chmod($f): $!"; + my $mtime = delete $self->{'mtime._/text/config/raw'}; + $fh->flush or die "flush($f): $!"; + if (defined $mtime) { + utime($mtime, $mtime, $fh) or die "utime($f): $!"; + } my $cfg = PublicInbox::Config->git_config_dump($f, $self->{lei}->{2}); my $ibx = $self->{ibx} = {}; for my $sec (grep(/\Apublicinbox\./, @{$cfg->{-section_order}})) { @@ -134,35 +181,41 @@ sub _try_config { sub set_description ($) { my ($self) = @_; - my $f = "$self->{dst}/description"; + my $dst = $self->{cur_dst} // $self->{dst}; + my $f = "$dst/description"; open my $fh, '+>>', $f or die "open($f): $!"; seek($fh, 0, SEEK_SET) or die "seek($f): $!"; - chomp(my $d = do { local $/; <$fh> } // die "read($f): $!"); - if ($d eq '($INBOX_DIR/description missing)' || - $d =~ /^Unnamed repository/ || $d !~ /\S/) { - seek($fh, 0, SEEK_SET) or die "seek($f): $!"; - truncate($fh, 0) or die "truncate($f): $!"; - print $fh "mirror of $self->{src}\n" or die "print($f): $!"; - close $fh or die "close($f): $!"; + my $d = do { local $/; <$fh> } // die "read($f): $!"; + chomp(my $orig = $d); + while (defined($d) && ($d =~ m!^\(\$INBOX_DIR/description missing\)! || + $d =~ /^Unnamed repository/ || $d !~ /\S/)) { + $d = delete($self->{'txt.description'}); } + $d //= 'mirror of '.($self->{cur_src} // $self->{src}); + chomp $d; + return if $d eq $orig; + seek($fh, 0, SEEK_SET) or die "seek($f): $!"; + truncate($fh, 0) or die "truncate($f): $!"; + print $fh $d, "\n" or die "print($f): $!"; + close $fh or die "close($f): $!"; } sub index_cloned_inbox { my ($self, $iv) = @_; my $lei = $self->{lei}; - my $err = _get_txt($self, qw(description description)); - warn($err, "\n") if $err; # non fatal eval { set_description($self) }; warn $@ if $@; # n.b. public-inbox-clone works w/o (SQLite || Xapian) # lei is useless without Xapian + SQLite if ($lei->{cmd} ne 'public-inbox-clone') { + require PublicInbox::InboxWritable; + require PublicInbox::Admin; my $ibx = delete($self->{ibx}) // { address => [ 'lei@example.com' ], version => $iv, }; - $ibx->{inboxdir} = $self->{dst}; + $ibx->{inboxdir} = $self->{cur_dst} // $self->{dst}; PublicInbox::Inbox->new($ibx); PublicInbox::InboxWritable->new($ibx); my $opt = {}; @@ -178,41 +231,59 @@ sub index_cloned_inbox { PublicInbox::Admin::progress_prepare($opt, $lei->{2}); PublicInbox::Admin::index_inbox($ibx, undef, $opt); } + return if defined $self->{cur_dst}; # one of many repos to clone open my $x, '>', "$self->{dst}/mirror.done"; # for _wq_done_wait } sub run_reap { my ($lei, $cmd, $opt) = @_; $lei->qerr("# @$cmd"); - $opt->{pgid} = 0 if $lei->{sock}; - my $pid = spawn($cmd, undef, $opt); - my $reap = PublicInbox::OnDestroy->new($lei->can('sigint_reap'), $pid); - waitpid($pid, 0) == $pid or die "waitpid @$cmd: $!"; - @$reap = (); # cancel reap + waitpid(spawn($cmd, undef, $opt), 0) // die "waitpid: $!"; my $ret = $?; $? = 0; # don't let it influence normal exit $ret; } +sub start_clone { + my ($self, $cmd, $opt, $fini) = @_; + my $jobs = $self->{lei}->{opt}->{jobs} // 1; + reap_live() while keys(%$LIVE) >= $jobs; + $self->{lei}->qerr("# @$cmd"); + return if $self->{dry_run}; + $LIVE->{spawn($cmd, undef, $opt)} = [ \&reap_clone, $self, $cmd, $fini ] +} + sub clone_v1 { - my ($self) = @_; + my ($self, $nohang) = @_; my $lei = $self->{lei}; my $curl = $self->{curl} //= PublicInbox::LeiCurl->new($lei) or return; - my $uri = URI->new($self->{src}); + my $uri = URI->new($self->{cur_src} // $self->{src}); defined($lei->{opt}->{epoch}) and die "$uri is a v1 inbox, --epoch is not supported\n"; my $pfx = $curl->torsocks($lei, $uri) or return; - my $cmd = [ @$pfx, clone_cmd($lei, my $opt = {}), - $uri->as_string, $self->{dst} ]; - my $cerr = run_reap($lei, $cmd, $opt); - return $lei->child_error($cerr, "@$cmd failed") if $cerr; - _try_config($self); - write_makefile($self->{dst}, 1); - index_cloned_inbox($self, 1); + my $dst = $self->{cur_dst} // $self->{dst}; + my $fini = PublicInbox::OnDestroy->new($$, \&v1_done, $self); + my $cmd = [ @$pfx, clone_cmd($lei, my $opt = {}), "$uri", $dst ]; + my $ref = $self->{-ent} ? $self->{-ent}->{reference} : undef; + defined($ref) && -e "$self->{dst}$ref" and + push @$cmd, '--reference', "$self->{dst}$ref"; + start_clone($self, $cmd, $opt, $fini); + + if (!$self->{-is_epoch} && $lei->{opt}->{'inbox-config'} =~ + /\A(?:always|v1)\z/s) { + _get_txt_start($self, '_/text/config/raw', $fini); + } + + my $d = $self->{-ent} ? $self->{-ent}->{description} : undef; + $self->{'txt.description'} = $d if defined $d; + (!defined($d) && !$nohang) and + _get_txt_start($self, 'description', $fini); + + reap_live() until ($nohang || !keys(%$LIVE)); # for non-manifest clone } sub parse_epochs ($$) { - my ($opt_epochs, $v2_epochs) = @_; # $epcohs "LOW..HIGH" + my ($opt_epochs, $v2_epochs) = @_; # $epochs "LOW..HIGH" $opt_epochs // return; # undef => all epochs my ($lo, $dotdot, $hi, @extra) = split(/(\.\.)/, $opt_epochs); undef($lo) if ($lo // '') eq ''; @@ -254,8 +325,8 @@ EOM $want } -sub init_placeholder ($$) { - my ($src, $edst) = @_; +sub init_placeholder ($$$) { + my ($src, $edst, $ent) = @_; PublicInbox::Import::init_bare($edst); my $f = "$edst/config"; open my $fh, '>>', $f or die "open($f): $!"; @@ -267,20 +338,104 @@ sub init_placeholder ($$) { ; This git epoch was created read-only and "public-inbox-fetch" ; will not fetch updates for it unless write permission is added. +; Hint: chmod +w $edst +EOM + if (defined($ent->{owner})) { + print $fh <{owner} EOM - close $fh or die "close:($f): $!"; + } + close $fh or die "close($f): $!"; + my %map = (head => 'HEAD', description => undef); + while (my ($key, $fn) = each %map) { + my $val = $ent->{$key} // next; + $fn //= $key; + $fn = "$edst/$fn"; + open $fh, '>', $fn or die "open($fn): $!"; + print $fh $val, "\n" or die "print($fn): $!"; + close $fh or die "close($fn): $!"; + } +} + +sub reap_clone { # async, called via SIGCHLD + my ($self, $cmd) = @_; + my $cerr = $?; + $? = 0; # don't let it influence normal exit + if ($cerr) { + kill('TERM', keys %$LIVE); + $self->{lei}->child_error($cerr, "@$cmd failed"); + } +} + +sub v1_done { # called via OnDestroy + my ($self) = @_; + return if $self->{dry_run} || !$LIVE; + _write_inbox_config($self); + my $dst = $self->{cur_dst} // $self->{dst}; + if (defined(my $o = $self->{-ent} ? $self->{-ent}->{owner} : undef)) { + run_die([qw(git config -f), "$dst/config", 'gitweb.owner', $o]); + } + my $o = "$dst/objects"; + if (open(my $fh, '<', "$o/info/alternates")) { + chomp(my @l = <$fh>); + for (@l) { $_ = File::Spec->abs2rel($_, $o)."\n" } + my $f = File::Temp->new(TEMPLATE => '.XXXX', DIR => "$o/info"); + print $f @l; + $f->flush or die "flush($f): $!"; + rename($f->filename, "$o/info/alternates") or + die "rename($f, $o/info/alternates): $!"; + $f->unlink_on_destroy(0); + } + return if $self->{-is_epoch}; + write_makefile($dst, 1); + index_cloned_inbox($self, 1); +} + +sub v2_done { # called via OnDestroy + my ($self) = @_; + return if $self->{dry_run} || !$LIVE; + my $dst = $self->{cur_dst} // $self->{dst}; + require PublicInbox::Lock; + my $lk = bless { lock_path => "$dst/inbox.lock" }, 'PublicInbox::Lock'; + my $lck = $lk->lock_for_scope($$); + _write_inbox_config($self); + require PublicInbox::MultiGit; + my $mg = PublicInbox::MultiGit->new($dst, 'all.git', 'git'); + $mg->fill_alternates; + for my $i ($mg->git_epochs) { $mg->epoch_cfg_set($i) } + for my $edst (@{delete($self->{-read_only}) // []}) { + my @st = stat($edst) or die "stat($edst): $!"; + chmod($st[2] & 0555, $edst) or die "chmod(a-w, $edst): $!"; + } + write_makefile($dst, 2); + undef $lck; # unlock + index_cloned_inbox($self, 2); } -sub clone_v2 ($$;$) { +sub reap_live { + my $pid = waitpid(-1, 0) // die "waitpid(-1): $!"; + if (my $x = delete $LIVE->{$pid}) { + my $cb = shift @$x; + $cb->(@$x); + } else { + warn "reaped unknown PID=$pid ($?)\n"; + } +} + +sub clone_v2_prep ($$;$) { my ($self, $v2_epochs, $m) = @_; # $m => manifest.js.gz hashref my $lei = $self->{lei}; my $curl = $self->{curl} //= PublicInbox::LeiCurl->new($lei) or return; - my $pfx = $curl->torsocks($lei, (values %$v2_epochs)[0]) or return; - my $dst = $self->{dst}; + my $first_uri = (map { $_->[0] } values %$v2_epochs)[0]; + my $pfx = $curl->torsocks($lei, $first_uri) or return; + my $dst = $self->{cur_dst} // $self->{dst}; my $want = parse_epochs($lei->{opt}->{epoch}, $v2_epochs); - my (@src_edst, @read_only, @skip_nr); + my $task = $m ? bless { %$self }, __PACKAGE__ : $self; + delete $task->{todo}; # $self->{todo} still exists + my (@src_edst, @skip, $desc, @entv); for my $nr (sort { $a <=> $b } keys %$v2_epochs) { - my $uri = $v2_epochs->{$nr}; + my ($uri, $key) = @{$v2_epochs->{$nr}}; my $src = $uri->as_string; my $edst = $dst; $src =~ m!/([0-9]+)(?:\.git)?\z! or die <<""; @@ -288,54 +443,48 @@ failed to extract epoch number from $src $1 + 0 == $nr or die "BUG: <$uri> miskeyed $1 != $nr"; $edst .= "/git/$nr.git"; + my $ent; + if ($m) { + $ent = $m->{$key} // + die("BUG: `$key' not in manifest.js.gz"); + if (defined(my $d = $ent->{description})) { + $d =~ s/ \[epoch [0-9]+\]\z//s; + $desc = $d; + } + } if (!$want || $want->{$nr}) { push @src_edst, $src, $edst; + push @entv, $edst, $ent; + $self->{any_want}->{$key} = 1; } else { # create a placeholder so users only need to chmod +w - init_placeholder($src, $edst); - push @read_only, $edst; - push @skip_nr, $nr; + init_placeholder($src, $edst, $ent); + push @{$task->{-read_only}}, $edst; + push @skip, $key; } } - if (@skip_nr) { # filter out the epochs we skipped - my $re = join('|', @skip_nr); - my @del = grep(m!/git/$re\.git\z!, keys %$m); - delete @$m{@del}; - $self->{-culled_manifest} = 1; - } - my $lk = bless { lock_path => "$dst/inbox.lock" }, 'PublicInbox::Lock'; - _try_config($self); - my $on_destroy = $lk->lock_for_scope($$); - my @cmd = clone_cmd($lei, my $opt = {}); - while (my ($src, $edst) = splice(@src_edst, 0, 2)) { - my $cmd = [ @$pfx, @cmd, $src, $edst ]; - my $cerr = run_reap($lei, $cmd, $opt); - return $lei->child_error($cerr, "@$cmd failed") if $cerr; - } - require PublicInbox::MultiGit; - my $mg = PublicInbox::MultiGit->new($dst, 'all.git', 'git'); - $mg->fill_alternates; - for my $i ($mg->git_epochs) { $mg->epoch_cfg_set($i) } - for my $edst (@read_only) { - my @st = stat($edst) or die "stat($edst): $!"; - chmod($st[2] & 0555, $edst) or die "chmod(a-w, $edst): $!"; + # filter out the epochs we skipped + $self->{-culled_manifest} = 1 if $m && delete(@$m{@skip}); + + (!$self->{dry_run} && !-d $dst) and File::Path::mkpath($dst); + + my $fini = PublicInbox::OnDestroy->new($$, \&v2_done, $task); + + $lei->{opt}->{'inbox-config'} =~ /\A(?:always|v2)\z/s and + _get_txt_start($task, '_/text/config/raw', $fini); + + defined($desc) ? ($task->{'txt.description'} = $desc) : + _get_txt_start($task, 'description', $fini); + while (@entv) { + my ($edst, $ent) = splice(@entv, 0, 2); + my $etask = bless { %$task }, __PACKAGE__; + $etask->{-ent} = $ent; # may have {reference} + $etask->{cur_src} = shift @src_edst // die 'BUG: no cur_src'; + $etask->{cur_dst} = shift @src_edst // die 'BUG: no cur_dst'; + $etask->{cur_dst} eq $edst or + die "BUG: `$etask->{cur_dst}' != `$edst'"; + $etask->{-is_epoch} = $fini; + push @{$self->{todo}->{($ent->{reference} // '')}}, $etask; } - write_makefile($self->{dst}, 2); - undef $on_destroy; # unlock - index_cloned_inbox($self, 2); -} - -# PSGI mount prefixes and manifest.js.gz prefixes don't always align... -sub deduce_epochs ($$) { - my ($m, $path) = @_; - my ($v1_ent, @v2_epochs); - my $path_pfx = ''; - $path =~ s!/+\z!!; - do { - $v1_ent = $m->{$path}; - @v2_epochs = grep(m!\A\Q$path\E/git/[0-9]+\.git\z!, keys %$m); - } while (!defined($v1_ent) && !@v2_epochs && - $path =~ s!\A(/[^/]+)/!/! and $path_pfx .= $1); - ($path_pfx, $v1_ent ? $path : undef, @v2_epochs); } sub decode_manifest ($$$) { @@ -350,6 +499,103 @@ sub decode_manifest ($$$) { $m; } +sub multi_inbox ($$$) { + my ($self, $path, $m) = @_; + my $incl = $self->{lei}->{opt}->{include}; + my $excl = $self->{lei}->{opt}->{exclude}; + + # assuming everything not v2 is v1, for now + my @v1 = sort grep(!m!.+/git/[0-9]+\.git\z!, keys %$m); + my @v2_epochs = sort grep(m!.+/git/[0-9]+\.git\z!, keys %$m); + my $v2 = {}; + + for (@v2_epochs) { + m!\A(/.+)/git/[0-9]+\.git\z! or die "BUG: $_"; + push @{$v2->{$1}}, $_; + } + my $n = scalar(keys %$v2) + scalar(@v1); + my @orig = defined($incl // $excl) ? (keys %$v2, @v1) : (); + if (defined $incl) { + my $re = '(?:'.join('\\z|', map { + $self->{lei}->glob2re($_) // qr/\A\Q$_\E/ + } @$incl).'\\z)'; + my @gone = delete @$v2{grep(!/$re/, keys %$v2)}; + delete @$m{map { @$_ } @gone} and $self->{-culled_manifest} = 1; + delete @$m{grep(!/$re/, @v1)} and $self->{-culled_manifest} = 1; + @v1 = grep(/$re/, @v1); + } + if (defined $excl) { + my $re = '(?:'.join('\\z|', map { + $self->{lei}->glob2re($_) // qr/\A\Q$_\E/ + } @$excl).'\\z)'; + my @gone = delete @$v2{grep(/$re/, keys %$v2)}; + delete @$m{map { @$_ } @gone} and $self->{-culled_manifest} = 1; + delete @$m{grep(/$re/, @v1)} and $self->{-culled_manifest} = 1; + @v1 = grep(!/$re/, @v1); + } + my $ret; # { v1 => [ ... ], v2 => { "/$inbox_name" => [ epochs ] }} + $ret->{v1} = \@v1 if @v1; + $ret->{v2} = $v2 if keys %$v2; + $ret //= @orig ? "Nothing to clone, available repositories:\n\t". + join("\n\t", sort @orig) + : "Nothing available to clone\n"; + my $path_pfx = ''; + + # PSGI mount prefixes and manifest.js.gz prefixes don't always align... + if (@v2_epochs) { + until (grep(m!\A\Q$$path\E/git/[0-9]+\.git\z!, + @v2_epochs) == @v2_epochs) { + $$path =~ s!\A(/[^/]+)/!/! or last; + $path_pfx .= $1; + } + } elsif (@v1) { + while (!defined($m->{$$path}) && $$path =~ s!\A(/[^/]+)/!/!) { + $path_pfx .= $1; + } + } + ($path_pfx, $n, $ret); +} + +sub clone_all { + my ($self, $m) = @_; + my $todo = delete $self->{todo}; + my $nodep = delete $todo->{''}; + + # do not download unwanted deps + my $any_want = delete $self->{any_want}; + my @unwanted = grep { !$any_want->{$_} } keys %$todo; + my @nodep = delete(@$todo{@unwanted}); + push(@$nodep, @$_) for @nodep; + + # handle no-dependency repos, first + for (@$nodep) { + clone_v1($_, 1); + return if $self->{lei}->{child_error}; + } + # resolve references, deepest, first: + while (scalar keys %$todo) { + for my $x (keys %$todo) { + my ($nr, $nxt); + # resolve multi-level references + while ($m && defined($nxt = $m->{$x}->{reference})) { + exists($todo->{$nxt}) or last; + die < 1000; +E: dependency loop detected (`$x' => `$nxt') +EOM + $x = $nxt; + } + my $y = delete $todo->{$x} // next; # already done + for (@$y) { + clone_v1($_, 1); + return if $self->{lei}->{child_error}; + } + last; # restart %$todo iteration + } + } + reap_live() while keys(%$LIVE); +} + +# FIXME: this gets confused by single inbox instance w/ global manifest.js.gz sub try_manifest { my ($self) = @_; my $uri = URI->new($self->{src}); @@ -358,16 +604,12 @@ sub try_manifest { my $path = $uri->path; chop($path) eq '/' or die "BUG: $uri not canonicalized"; $uri->path($path . '/manifest.js.gz'); - my $pdir = $lei->rel2abs($self->{dst}); - $pdir =~ s!/[^/]+/?\z!!; - my $ft = File::Temp->new(TEMPLATE => 'm-XXXX', - UNLINK => 1, DIR => $pdir, SUFFIX => '.tmp'); + my $ft = File::Temp->new(TEMPLATE => '.manifest-XXXX', + UNLINK => 1, TMPDIR => 1, SUFFIX => '.tmp'); my $fn = $ft->filename; - my ($bn) = ($fn =~ m!/([^/]+)\z!); - my $cmd = $curl->for_uri($lei, $uri, '-R', '-o', $bn); - my $opt = { -C => $pdir }; - $opt->{$_} = $lei->{$_} for (0..2); - my $cerr = run_reap($lei, $cmd, $opt); + my $cmd = $curl->for_uri($lei, $uri, qw(-f -R -o), $fn); + my %opt = map { $_ => $lei->{$_} } (0..2); + my $cerr = run_reap($lei, $cmd, \%opt); if ($cerr) { return try_scrape($self) if ($cerr >> 8) == 22; # 404 missing return $lei->child_error($cerr, "@$cmd failed"); @@ -377,36 +619,74 @@ sub try_manifest { warn $@; return try_scrape($self); } - my ($path_pfx, $v1_path, @v2_epochs) = deduce_epochs($m, $path); - if (@v2_epochs) { - # It may be possible to have v1 + v2 in parallel someday: - warn(<child_error(1, $multi) if !ref($multi); + my $v2 = delete $multi->{v2}; + local $self->{todo} = {}; + if ($v2) { + for my $name (sort keys %$v2) { + my $epochs = delete $v2->{$name}; + my %v2_epochs = map { + $uri->path($n > 1 ? $path_pfx.$path.$_ + : $path_pfx.$_); + my ($e) = ("$uri" =~ m!/([0-9]+)\.git\z!); + $e // die "no [0-9]+\.git in `$uri'"; + $e => [ $uri->clone, $_ ]; + } @$epochs; + ("$uri" =~ m!\A(.+/)git/[0-9]+\.git\z!) or + die "BUG: `$uri' !~ m!/git/[0-9]+.git!"; + local $self->{cur_src} = $1; + local $self->{cur_dst} = $self->{dst}; + if ($n > 1 && $uri->path =~ m!\A\Q$path_pfx$path\E/(.+)/ + git/[0-9]+\.git\z!x) { + $self->{cur_dst} .= "/$1"; + } + index($self->{cur_dst}, "\n") >= 0 and die <{cur_dst}' must not contain newline EOM - my %v2_epochs = map { - $uri->path($path_pfx.$_); - my ($n) = ("$uri" =~ m!/([0-9]+)\.git\z!); - $n => $uri->clone - } @v2_epochs; - clone_v2($self, \%v2_epochs, $m); - } elsif (defined $v1_path) { - clone_v1($self); - } else { - die "E: confused by <$uri>, possible matches:\n\t", - join(', ', sort keys %$m), "\n"; + clone_v2_prep($self, \%v2_epochs, $m); + return if $self->{lei}->{child_error}; + } } - if (delete $self->{-culled_manifest}) { # set by clone_v2 + if (my $v1 = delete $multi->{v1}) { + my $p = $path_pfx.$path; + chop($p) if substr($p, -1, 1) eq '/'; + $uri->path($p); + for my $name (@$v1) { + my $task = bless { %$self }, __PACKAGE__; + $task->{-ent} = $m->{$name} // + die("BUG: no `$name' in manifest"); + $task->{cur_src} = "$uri"; + $task->{cur_dst} = $task->{dst}; + if ($n > 1) { + $task->{cur_dst} .= $name; + $task->{cur_src} .= $name; + } + index($task->{cur_dst}, "\n") >= 0 and die <{cur_dst}' must not contain newline +EOM + $task->{cur_src} .= '/'; + my $dep = $task->{-ent}->{reference} // ''; + push @{$self->{todo}->{$dep}}, $task; # for clone_all + $self->{any_want}->{$name} = 1; + } + } + delete local $lei->{opt}->{epoch} if defined($v2); + clone_all($self, $m); + return if $self->{lei}->{child_error} || $self->{dry_run}; + + # set by clone_v2_prep/-I/--exclude + if (delete $self->{-culled_manifest}) { # write the smaller manifest if epochs were skipped so # users won't have to delete manifest if they +w an # epoch they no longer want to skip my $json = PublicInbox::Config->json->encode($m); + my $mtime = (stat($fn))[9]; gzip(\$json => $fn) or die "gzip: $GzipError"; + utime($mtime, $mtime, $fn) or die "utime(..., $fn): $!"; } - my $fin = "$self->{dst}/manifest.js.gz"; - rename($fn, $fin) or die "E: rename($fn, $fin): $!"; - $ft->unlink_on_destroy(0); + ft_rename($ft, "$self->{dst}/manifest.js.gz", 0666); + open my $x, '>', "$self->{dst}/mirror.done"; # for _wq_done_wait } sub start_clone_url { @@ -415,18 +695,24 @@ sub start_clone_url { die "TODO: non-HTTP/HTTPS clone of $self->{src} not supported, yet"; } -sub do_mirror { # via wq_io_do +sub do_mirror { # via wq_io_do or public-inbox-clone my ($self) = @_; my $lei = $self->{lei}; + umask($lei->{client_umask}) if defined $lei->{client_umask}; eval { - my $iv = $lei->{opt}->{'inbox-version'}; - if (defined $iv) { - return clone_v1($self) if $iv == 1; - return try_scrape($self) if $iv == 2; - die "bad --inbox-version=$iv\n"; - } - return start_clone_url($self) if $self->{src} =~ m!://!; - die "TODO: cloning local directories not supported, yet"; + my $ic = $lei->{opt}->{'inbox-config'} //= 'always'; + $ic =~ /\A(?:v1|v2|always|never)\z/s or die <<""; +--inbox-config must be one of `always', `v2', `v1', or `never' + + local $LIVE; + my $iv = $lei->{opt}->{'inbox-version'} // + return start_clone_url($self); + return clone_v1($self) if $iv == 1; + die "bad --inbox-version=$iv\n" if $iv != 2; + die <{src} !~ m!://!; +cloning local v2 inboxes not supported +EOM + try_scrape($self, 1); }; $lei->fail($@) if $@; } @@ -434,25 +720,17 @@ sub do_mirror { # via wq_io_do sub start { my ($cls, $lei, $src, $dst) = @_; my $self = bless { src => $src, dst => $dst }, $cls; - if ($src =~ m!https?://!) { - require URI; - require PublicInbox::LeiCurl; - } - require PublicInbox::Lock; - require PublicInbox::Inbox; - require PublicInbox::Admin; - require PublicInbox::InboxWritable; + $lei->request_umask; my ($op_c, $ops) = $lei->workers_start($self, 1); $lei->{wq1} = $self; $self->wq_io_do('do_mirror', []); - $self->wq_close(1); + $self->wq_close; $lei->wait_wq_events($op_c, $ops); } sub ipc_atfork_child { my ($self) = @_; $self->{lei}->_lei_atfork_child; - $SIG{TERM} = sub { exit(128 + 15) }; # trigger OnDestroy $reap $self->SUPER::ipc_atfork_child; }